Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
中文简介正在准备中。当前显示原文说明。
Orchestrates Spec Driven Development by coordinating spec, plan, and task skills. Use when running the full speckit workflow from spec to implementation.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Coordinates the Spec Driven Development workflow, skill loading, and progress tracking throughout the command lifecycle.
Treat SDD as a minimal, testable "self-modeling" loop:
spec.md, plan.md, tasks.md).specify/memory/constitution.md) + progress stateThis mirrors patterns from open-ended embodied agents (e.g., Voyager/MineDojo) that compound capability via a curriculum (tasks.md) and a skill library (reusable plugin skills and superpowers methodology skills).
/speckit-* command.Verify Repository Context
.specify/ directory structure.Load Persistent State ("presence")
.specify/memory/constitution.md for constraints/principles.spec.md / plan.md / tasks.md context if present.Load Command Dependencies
Initialize Progress Tracking
Quick reference for command-to-skill mappings:
| Command | Primary Skill | Complementary Skills |
|---|---|---|
/speckit-specify | spec-writing | brainstorming |
/speckit-clarify | spec-writing | brainstorming |
/speckit-plan | task-planning | writing-plans |
/speckit-tasks | task-planning | executing-plans |
/speckit-implement | - | executing-plans, systematic-debugging |
/speckit-converge | - | executing-plans, verification-before-completion |
/speckit-analyze | - | systematic-debugging, verification |
/speckit-checklist | - | verification-before-completion |
For detailed patterns: See modules/command-skill-matrix.md for complete mappings and loading rules.
See modules/writing-plans-extensions.md for plan authoring patterns.
For each workflow session, track:
For detailed patterns: See modules/progress-tracking.md for TodoWrite patterns and metrics.
spec-writing: Specification creation and refinement.task-planning: Task generation and planning.superpowers:brainstorming: Idea refinement.superpowers:writing-plans: Implementation planning.superpowers:executing-plans: Task execution.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
中文简介正在准备中。当前显示原文说明。
Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.
中文简介正在准备中。当前显示原文说明。
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.
中文简介正在准备中。当前显示原文说明。
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
中文简介正在准备中。当前显示原文说明。
Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.
中文简介正在准备中。当前显示原文说明。
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
中文简介正在准备中。当前显示原文说明。